linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Al Viro <viro@ZenIV.linux.org.uk>
To: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Miklos Szeredi <mszeredi@suse.cz>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>
Subject: Re: fs/dcache.c - BUG: soft lockup - CPU#5 stuck for 22s! [systemd-udevd:1667]
Date: Wed, 28 May 2014 19:39:54 +0100	[thread overview]
Message-ID: <20140528183954.GA18016@ZenIV.linux.org.uk> (raw)
In-Reply-To: <20140528141937.GZ18016@ZenIV.linux.org.uk>

On Wed, May 28, 2014 at 03:19:37PM +0100, Al Viro wrote:

> OK, it's not ->i_lock, it's ->d_lock on parent being grabbed after that on
> child, while d_walk() keeps taking them in opposite order.  Hmm...
> 
> In principle we could do the following:
> 	* split dentry_kill() into the part that is taking locks and
> the rest of it.
> 	* in case of trylock failure have shrink_dentry_list() do
> read_seqlock_excl(&rename_lock) (which will stabilize ->d_parent) and
> take ->d_lock in the right order, drop rename_lock and call __dentry_kill().
> 
> AFAICS, that would kill the livelock for good.  We still have ->i_lock
> trylock failures to deal with, but those are less of a problem - d_walk()
> won't step on ->i_lock at all.  I'm going to grab a couple of hours of sleep
> and try to put together something along those lines...

OK, the warnings about averting your eyes very much apply; the thing below
definitely needs more massage before it becomes acceptable (and no, it's
not a single commit; I'm not that insane), but it changes behaviour in the
way described above.  Could you check if the livelock persists with it?
No trace-generating code in there, so the logs should be compact enough...

diff --git a/fs/dcache.c b/fs/dcache.c
index 42ae01e..ed0cc62 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -441,42 +441,12 @@ void d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(d_drop);
 
-/*
- * Finish off a dentry we've decided to kill.
- * dentry->d_lock must be held, returns with it unlocked.
- * If ref is non-zero, then decrement the refcount too.
- * Returns dentry requiring refcount drop, or NULL if we're done.
- */
-static struct dentry *
-dentry_kill(struct dentry *dentry, int unlock_on_failure)
-	__releases(dentry->d_lock)
+static void __dentry_kill(struct dentry *dentry)
 {
-	struct inode *inode;
 	struct dentry *parent = NULL;
 	bool can_free = true;
-
-	if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) {
-		can_free = dentry->d_flags & DCACHE_MAY_FREE;
-		spin_unlock(&dentry->d_lock);
-		goto out;
-	}
-
-	inode = dentry->d_inode;
-	if (inode && !spin_trylock(&inode->i_lock)) {
-relock:
-		if (unlock_on_failure) {
-			spin_unlock(&dentry->d_lock);
-			cpu_relax();
-		}
-		return dentry; /* try again with same dentry */
-	}
 	if (!IS_ROOT(dentry))
 		parent = dentry->d_parent;
-	if (parent && !spin_trylock(&parent->d_lock)) {
-		if (inode)
-			spin_unlock(&inode->i_lock);
-		goto relock;
-	}
 
 	/*
 	 * The dentry is now unrecoverably dead to the world.
@@ -520,10 +490,44 @@ relock:
 		can_free = false;
 	}
 	spin_unlock(&dentry->d_lock);
-out:
 	if (likely(can_free))
 		dentry_free(dentry);
+}
+
+/*
+ * Finish off a dentry we've decided to kill.
+ * dentry->d_lock must be held, returns with it unlocked.
+ * If ref is non-zero, then decrement the refcount too.
+ * Returns dentry requiring refcount drop, or NULL if we're done.
+ */
+static struct dentry *
+dentry_kill(struct dentry *dentry, int unlock_on_failure)
+	__releases(dentry->d_lock)
+{
+	struct inode *inode = dentry->d_inode;
+	struct dentry *parent = NULL;
+
+	if (inode && unlikely(!spin_trylock(&inode->i_lock)))
+		goto failed;
+
+	if (!IS_ROOT(dentry)) {
+		parent = dentry->d_parent;
+		if (unlikely(!spin_trylock(&parent->d_lock))) {
+			if (inode)
+				spin_unlock(&inode->i_lock);
+			goto failed;
+		}
+	}
+
+	__dentry_kill(dentry);
 	return parent;
+
+failed:
+	if (unlock_on_failure) {
+		spin_unlock(&dentry->d_lock);
+		cpu_relax();
+	}
+	return dentry; /* try again with same dentry */
 }
 
 /* 
@@ -797,6 +801,7 @@ static void shrink_dentry_list(struct list_head *list)
 	struct dentry *dentry, *parent;
 
 	while (!list_empty(list)) {
+		struct inode *inode;
 		dentry = list_entry(list->prev, struct dentry, d_lru);
 		spin_lock(&dentry->d_lock);
 		/*
@@ -815,23 +820,52 @@ static void shrink_dentry_list(struct list_head *list)
 			continue;
 		}
 
-		parent = dentry_kill(dentry, 0);
-		/*
-		 * If dentry_kill returns NULL, we have nothing more to do.
-		 */
-		if (!parent)
+
+		if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) {
+			bool can_free = dentry->d_flags & DCACHE_MAY_FREE;
+			spin_unlock(&dentry->d_lock);
+			if (can_free)
+				dentry_free(dentry);
 			continue;
+		}
 
-		if (unlikely(parent == dentry)) {
-			/*
-			 * trylocks have failed and d_lock has been held the
-			 * whole time, so it could not have been added to any
-			 * other lists. Just add it back to the shrink list.
-			 */
+		inode = dentry->d_inode;
+		if (inode && unlikely(!spin_trylock(&inode->i_lock))) {
 			d_shrink_add(dentry, list);
 			spin_unlock(&dentry->d_lock);
 			continue;
 		}
+
+		if (IS_ROOT(dentry)) {
+			__dentry_kill(dentry);
+			continue;
+		}
+
+		parent = dentry->d_parent;
+		if (unlikely(!spin_trylock(&parent->d_lock))) {
+			if (inode)
+				spin_unlock(&inode->i_lock);
+			d_shrink_add(dentry, list);
+			spin_unlock(&dentry->d_lock);
+			read_seqlock_excl(&rename_lock);
+			parent = NULL;
+			if (!IS_ROOT(dentry)) {
+				parent = dentry->d_parent;
+				spin_lock(&parent->d_lock);
+			}
+			spin_lock(&dentry->d_lock);
+			read_sequnlock_excl(&rename_lock);
+			inode = dentry->d_inode;
+			if (inode && unlikely(!spin_trylock(&inode->i_lock))) {
+				if (parent)
+					spin_unlock(&parent->d_lock);
+				spin_unlock(&dentry->d_lock);
+				continue;
+			}
+			d_shrink_del(dentry);
+		}
+
+		__dentry_kill(dentry);
 		/*
 		 * We need to prune ancestors too. This is necessary to prevent
 		 * quadratic behavior of shrink_dcache_parent(), but is also

  reply	other threads:[~2014-05-28 18:39 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20140526093741.GA1765@lahna.fi.intel.com>
2014-05-26 13:57 ` fs/dcache.c - BUG: soft lockup - CPU#5 stuck for 22s! [systemd-udevd:1667] Al Viro
2014-05-26 14:29   ` Mika Westerberg
2014-05-26 15:27     ` Al Viro
2014-05-26 16:42       ` Al Viro
2014-05-26 18:17       ` Linus Torvalds
2014-05-26 18:26         ` Al Viro
2014-05-26 20:24           ` Linus Torvalds
2014-05-27  1:40             ` Al Viro
2014-05-27  3:14               ` Al Viro
2014-05-27  4:00                 ` Al Viro
2014-05-27  7:04                   ` Mika Westerberg
2014-05-28  3:19                     ` Al Viro
2014-05-28  7:37                       ` Mika Westerberg
2014-05-28 11:57                         ` Al Viro
2014-05-28 13:11                           ` Mika Westerberg
2014-05-28 14:19                             ` Al Viro
2014-05-28 18:39                               ` Al Viro [this message]
2014-05-28 19:43                                 ` Linus Torvalds
2014-05-28 20:02                                   ` Linus Torvalds
2014-05-28 20:25                                     ` Al Viro
2014-05-29 10:42                                     ` Mika Westerberg
2014-05-28 20:14                                   ` Al Viro
2014-05-28 21:11                                     ` Linus Torvalds
2014-05-28 21:28                                       ` Al Viro
2014-05-29  3:11                                 ` Al Viro
2014-05-29  3:52                                   ` Al Viro
2014-05-29  5:34                                     ` Al Viro
2014-05-29 10:51                                       ` Mika Westerberg
2014-05-29 11:04                                         ` Mika Westerberg
2014-05-29 13:30                                           ` Al Viro
2014-05-29 14:56                                             ` Mika Westerberg
2014-05-29 15:10                                             ` Linus Torvalds
2014-05-29 15:44                                               ` Al Viro
2014-05-29 16:23                                                 ` Al Viro
2014-05-29 16:29                                                   ` Linus Torvalds
2014-05-29 16:53                                                     ` Al Viro
2014-05-29 18:52                                                       ` Al Viro
2014-05-29 19:14                                                         ` Linus Torvalds
2014-05-30  4:50                                                           ` Al Viro
2014-05-30  5:00                                                             ` Linus Torvalds
2014-05-30  6:49                                                               ` Al Viro
2014-05-30  8:12                                                         ` Mika Westerberg
2014-05-30 15:21                                                           ` Al Viro
2014-05-30 15:31                                                             ` Linus Torvalds
2014-05-30 16:48                                                               ` [git pull] " Al Viro
2014-05-30 17:14                                                                 ` Al Viro
2014-05-31 14:18                                                                   ` Josh Boyer
2014-05-31 14:48                                                                     ` Linus Torvalds
2014-05-31 14:58                                                                       ` Josh Boyer
2014-05-31 16:12                                                                       ` Josh Boyer
2014-05-30 17:15                                                                 ` Sedat Dilek
2014-05-29  4:21                                   ` Linus Torvalds
2014-05-29  5:16                                     ` Al Viro
2014-05-29  5:26                                       ` Al Viro

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140528183954.GA18016@ZenIV.linux.org.uk \
    --to=viro@zeniv.linux.org.uk \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mika.westerberg@linux.intel.com \
    --cc=mszeredi@suse.cz \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).